About Me

Intro.

Hi, this is Liang Chen (陈亮). I'm a third-year PhD student at the Institute of Computational Linguistics, Peking University advised by Baobao Chang.

Currently, I am interested in developing Multimodal Understanding and Generation with Foundation Models. Please feel free to contact and discuss. Google Scholar Page

Education

2022.07 ~ Now: School of Computer Science, Peking University, PhD student

2018.09 ~ 2022.06: School of Software, Jilin University, Honours degree, majoring in Software Engineering, Pilot Class

Experiences

I have been fortunately collaborating and doing research with/in:

2022-2023: Microsoft Research Asia, Natural Language Computing Group

2023: Tencent, Tencent Cloud NLP Research Group

2023-2024: Alibaba, Qwen, VL Group

Academic Service

Reviewer: NeurIPS 2024, ACL Rolling Review 2022,2023,2024

Research Papers

* denotes equal contribution

✨✨A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation
[Code］
Liang Chen, Sinan Tan, Zefan Cai, Weichu Xie, Haozhe Zhao, Yichi Zhang, Junyang Lin, Jinze Bai, Tianyu Liu, Baobao Chang
arXiv Preprint

An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
[Code］[Demo]
Liang Chen, Haozhe Zhao, Tianyu Liu, Shuai Bai, Junyang Lin, Chang Zhou, Baobao Chang
ECCV 2024 (Oral, 2%)

MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation
[Homepage][Dataset］
Jinsheng Huang*, Liang Chen*, Taian Guo, Fu Zeng, Yusheng Zhao, Bohan Wu, Ye Yuan, Haozhe Zhao, Zhihui Guo, Yichi Zhang, Jingyang Yuan, Wei Ju, Luchen Liu, Tianyu Liu, Baobao Chang, Ming Zhang
arXiv Preprint

PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain
[Code］[Leaderboard］
Liang Chen, Yichi Zhang, Shuhuai Ren, Haozhe Zhao, Zefan Cai, Yuchi Wang, Peiyi Wang, Xiangdi Meng, Tianyu Liu, Baobao Chang
ACL-2024-Findings

Large language models are not fair evaluators
[Code］
Peiyi Wang, Lei Li, Liang Chen, Dawei Zhu, Binghuai Lin, Yunbo Cao, Qi Liu, Tianyu Liu, Zhifang Sui
ACL-2024

MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning
[Code］
Haozhe Zhao, Zefan Cai, Shuzheng Si, Xiaojian Ma, Kaikai An, Liang Chen, Zixuan Liu, Sheng Wang, Wenjuan Han, Baobao Chang
ICLR 2024

Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond
[Code］
Liang Chen, Yichi Zhang, Shuhuai Ren, Haozhe Zhao, Zefan Cai, Yuchi Wang, Tianyu Liu, Baobao Chang
Foundation Model for Decision Making Workshop @NeurIPS2023

Guiding AMR Parsing with Reverse Graph Linearization
[Code］
Bofei Gao*, Liang Chen*, Peiyi Wang, Zhifang Sui, Baobao Chang
EMNLP-2023-Findings

基于概念预测和关系预测的AMR解析与对齐方法
[Code］
陈亮，高博飞，张亦驰，常宝宝
《中文信息学报》

On the Pareto Front of Multilingual Neural Machine Translation
[Code］
Liang Chen*, Shuming Ma*, Dongdong Zhang, Furu Wei, Baobao Chang
NeurIPS 2023

On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation
[Code］
Liang Chen, Shuming Ma, Dongdong Zhang, Baobao Chang, Furu Wei
ACL-2023-Findings

A Two-Stage Method for Chinese AMR Parsing
[Code][Slides-ZH]
Liang Chen, Bofei Gao, Baobao Chang
CCL-2022 Workshop

ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRs
[Code][Slides-ZH]
Liang Chen*, Peiyi Wang*, Runxin Xu, Tianyu Liu, Zhifang Sui, Baobao Chang
NAACL-2022-Findings

Focus on the Target's Vocabulary: Masked Label Smoothing for Machine Translation
[Code][Slides-ZH][Slides-EN]
Liang Chen, Runxin Xu, Baobao Chang
ACL-2022

Hierarchical Curriculum Learning for AMR Parsing
[Code]
Peiyi Wang*,Liang Chen*, Tianyu Liu, Baobao Chang, Zhifang Sui
ACL-2022

DialogSum: A Real-Life Scenario Dialogue Summarization Dataset
[Code][Homepage]
Yulong Chen, Yang Liu, Liang Chen, Yue Zhang
ACL-2021-Findings

Crossed-Time Delay Neural Network for Speaker Recognition
[Code]
Liang Chen, Yanchun Liang, Xiaohu Shi, You Zhou, Chunguo Wu
MMM-2021

Patents

基于加权标签平滑的神经机器翻译模型训练方法[Link]
A Training Method for Neural Machine Translation Model Based on Weighted Label Smoothing
常宝宝;陈亮;许润昕

Awards

• National Scholarship, 2024
• Huawei Scholarship, 2023
• Win the 2nd Place in Chinese-AMR-Parsing-2022 Evaluation at CCL, 2022 [Link]
• Honours Degrees in Software Engineering & Outstanding Student Award, Jilin Unversity, 2022
• CCF Elite Collegiate Award, 2021 [Link]